How to calculate adjusted odds ratios and 95% CIs for GEE using proc genmod

[bsriv]

Hi all- relatively new to SAS, and these forums have been really helpful, but I'm using a GEE (rather than logistic regression) because i have data with repeated measures and multiple predictors, but I can't figure out how to just have a basic table of ORs, 95% CIs, and p values.  I have tried ESTIMATE and LSMEANS but it's not giving me what I want (the analyses look bivariate with both).  Here is my model:

proc genmod data=work.opioid27;

class BJH_MedRec countx (ref="1") racex (ref="1") agegrp (ref="2") narcanx (ref="1") alcoholx (ref="1") moodx (ref="1") sudx (ref="1") yr (ref="2005") / param=ref;

model suicidex=countx racex agegrp narcanx alcoholx moodx sudx yr / dist=bin link=logit;

repeated subject=BJH_MedRec / type=cs;

run;

Thanks!

[Rick_SAS]

Did you try using the EXP option on the ESTIMATE statement? See the GEE example on this web page.

[SAS_Rob · Accepted solution]

If you use the PARAM=GLM option on the CLASS statement then you will be able to use the ODDSRATIO option on the LSMEANS statement.  These estimates will all be adjusted for the other effects in the model.

proc genmod data=work.opioid27;

class BJH_MedRec countx (ref="1") racex (ref="1") agegrp (ref="2") narcanx (ref="1") alcoholx (ref="1") moodx (ref="1") sudx (ref="1") yr (ref="2005") / param=glm;

model suicidex=countx racex agegrp narcanx alcoholx moodx sudx yr / dist=bin link=logit;

repeated subject=BJH_MedRec / type=cs;

lsmeans countx racex agegrp narcanx alcoholx moodx sudx yr/diff oddsratio cl; 

run;

[bsriv]

Thank you!